TRACEALIGN -- Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs
"语义一致性" 相关文章
Sem-DPO: Mitigating Semantic Inconsistency in Preference Optimization for Prompt Engineering
The Recursive Coherence Principle: A Formal Constraint on Scalable Intelligence, Alignment, and Reasoning Architecture
Cleanse: Uncertainty Estimation Approach Using Clustering-based Semantic Consistency in LLMs
Coalescence - Determinism In Ways We Care About
跨模态通信总丢失语义、产生歧义？加入AI大模型，LAM-MSC实现四模态统一高效传输
